# TrimTail: Low-Latency Streaming ASR with Simple but Effective Spectrogram-Level Length Penalty

arXiv: https://arxiv.org/abs/2211.00522 · HTML: https://mlsanity.com/paper/2211.00522/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 18 references that are in the map.
- First posted on arXiv 1 Nov 2022.

## Builds on (most cited first, 11 of 11)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Conformer: Convolution-augmented Transformer for Speech Recognition](https://mlsanity.com/paper/2005.08100/) (2020)
- [Listen, Attend and Spell](https://mlsanity.com/paper/1508.01211/) (2015)
- [AISHELL-1: An Open-Source Mandarin Speech Corpus and A Speech Recognition Baseline](https://mlsanity.com/paper/1709.05522/) (2017)
- [FastEmit: Low-latency Streaming ASR with Sequence-level Emission Regularization](https://mlsanity.com/paper/2010.11148/) (2020)
- [Towards Fast and Accurate Streaming End-to-End ASR](https://mlsanity.com/paper/2004.11544/) (2020)
- [WeNet 2.0: More Productive End-to-End Speech Recognition Toolkit](https://mlsanity.com/paper/2203.15455/) (2022)
- [U2++: Unified Two-pass Bidirectional End-to-end Model for Speech Recognition](https://mlsanity.com/paper/2106.05642/) (2021)
- [Fast and Accurate Recurrent Neural Network Acoustic Models for Speech Recognition](https://mlsanity.com/paper/1507.06947/) (2015)
- [Dissecting User-Perceived Latency of On-Device E2E Speech Recognition](https://mlsanity.com/paper/2104.02207/) (2021)
- [Bayes risk CTC: Controllable CTC alignment in Sequence-to-Sequence tasks](https://mlsanity.com/paper/2210.07499/) (2022)

## Built on by (most cited first, 6 of 6)

- [ZeroPrompt: Streaming Acoustic Encoders are Zero-Shot Masked LMs](https://mlsanity.com/paper/2305.10649/) (2023)
- [Mamba for Streaming ASR Combined with Unimodal Aggregation](https://mlsanity.com/paper/2410.00070/) (2024)
- [Align With Purpose: Optimize Desired Properties in CTC Models with a General Plug-and-Play Framework](https://mlsanity.com/paper/2307.01715/) (2023)
- [Spiralformer: Low Latency Encoder for Streaming Speech Recognition with Circular Layer Skipping and Early Exiting](https://mlsanity.com/paper/2510.00982/) (2025)
- [Do we really need Self-Attention for Streaming Automatic Speech Recognition?](https://mlsanity.com/paper/2601.19960/) (2026)
- [SENS-ASR: Semantic Embedding injection in Neural-transducer for Streaming Automatic Speech Recognition](https://mlsanity.com/paper/2603.10005/) (2026)

## Abstract (arXiv)

In this paper, we present TrimTail, a simple but effective emission regularization method to improve the latency of streaming ASR models. The core idea of TrimTail is to apply length penalty (i.e., by trimming trailing frames, see Fig. 1-(b)) directly on the spectrogram of input utterances, which does not require any alignment. We demonstrate that TrimTail is computationally cheap and can be applied online and optimized with any training loss or any model architecture on any dataset without any extra effort by applying it on various end-to-end streaming ASR networks either trained with CTC loss [1] or Transducer loss [2]. We achieve 100 ~ 200ms latency reduction with equal or even better accuracy on both Aishell-1 and Librispeech. Moreover, by using TrimTail, we can achieve a 400ms algorithmic improvement of User Sensitive Delay (USD) with an accuracy loss of less than 0.2.